bpf, x64: save several bytes by using mov over movabsq when possible

Browse source

While analyzing some of the more complex BPF programs from Cilium,
I found that LLVM generally prefers to emit LD_IMM64 instead of MOV32
BPF instructions for loading unsigned 32-bit immediates into a
register. Given we cannot change the current/stable LLVM versions
that are already out there, lets optimize this case such that the
JIT prefers to emit 'mov %eax, imm32' over 'movabsq %rax, imm64'
whenever suitable in order to reduce the image size by 4-5 bytes per
such load in the typical case, reducing image size on some of the
bigger programs by up to 4%. emit_mov_imm32() and emit_mov_imm64()
have been added as helpers.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

...

This commit is contained in:

Daniel Borkmann 2018-02-24 01:07:59 +01:00 • committed by Alexei Starovoitov

parent 88e69a1fcc

commit 6fe8b9c1f4

1 changed files with 74 additions and 51 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download patch file Download diff file Expand all files Collapse all files

125

arch/x86/net/bpf_jit_comp.c

View file